,
,
,
Artificial intelligence (AI) is reshaping personalized medicine by enabling earlier diagnosis, tailored therapies, and faster drug discovery. The aim of the paper was to synthesize current evidence on AI applications in precision healthcare and quantify their impact on diagnostics, therapeutic decision-making, and discovery. We conducted a systematic review (2015–2024) with descriptive quantitative analysis across PubMed, Scopus, IEEE Xplore, and Web of Science. Fifty peer-reviewed studies met inclusion criteria (reporting sensitivity/specificity/accuracy or real-world deployment). We additionally summarized three case studies (oncologic imaging, rheumatoid arthritis treatment selection, and AI-accelerated discovery for glioblastoma). In oncology imaging, AI achieved high performance; the best lung-nodule model reported sensitivity at 95% and specificity at 94%. In chronic-disease therapeutics, AI tools predicted responses to DMARDs with ~87% accuracy, reduced adverse drug reactions by ~30%, and cut time-to-decision by ~85%. For discovery pipelines, AI screens compressed candidate identification by ~85%, yielding viable molecules within weeks. In diabetes management, AI-enabled predictive analytics achieved ~95% prediction accuracy, reduced hyperglycemic episodes by ~40%, and improved patient satisfaction. Evidence indicates that AI enhances diagnostic accuracy, personalizes therapy, and accelerates discovery while improving efficiency in chronic-disease management. Real-world adoption will depend on mitigating algorithmic bias, safeguarding privacy, expanding representative datasets, and deploying transparent, clinically interpretable models within clear regulatory frameworks.
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
The statements, opinions and data contained in the journal are solely those of the individual authors and contributors and not of the publisher and the editor(s). We stay neutral with regard to jurisdictional claims in published maps and institutional affiliations.